首页|SafeRespirator: Comprehensive Database for N95 Filtering Facepiece Respirator Leakage Detection Including Infrared, RGB Videos, and Quantitative Fit Testing

SafeRespirator: Comprehensive Database for N95 Filtering Facepiece Respirator Leakage Detection Including Infrared, RGB Videos, and Quantitative Fit Testing

扫码查看
原文链接
  • NETL
  • NSTL
  • IEEE
The COVID-19 pandemic underscored the challenges of performing mandatory Quantitative Fit Tests (QNFT) for healthcare professionals and the limitations of self-administered fit checks. To address this, it is crucial to develop faster and more efficient methods for detecting, locating, and quantifying Filtering Facepiece Respirators (FFRs) leakage, providing wearers with immediate feedback on their safety. Infrared (IR) technology, which relies on temperature variation analysis around the face seal, has proven effective for locating leakage but has not yet achieved automated quantification. This paper introduces a validated protocol for creating a comprehensive database to advance automatic leakage detection. The database includes synchronized and calibrated IR and RGB video data, along with QNFT results, collected from 62 participants wearing four different N95 FFR models in four distinct positions. High-performance IR and RGB cameras were used to precisely capture temperature variations, while a PortaCount® instrument served as the reference for fit quantification. Preliminary results using the MediaPipe approach with synchronized and calibrated RGB and IR videos demonstrate that precise tracking of the human face is achievable even with an FFR. The normalized cross-correlation methods further highlight the capability of IR imaging to accurately monitor and detect leakage. This breakthrough paves the way for real-time, automated detection of N95 FFR leakage, potentially deployable at operator workstations. This large, high-quality, open-access database is available to the scientific community to drive innovation in respiratory protection research and beyond.

Face masksCamerasFacesVideosImagingData collectionTestingSealsLensesDatabases

Geoffrey Marchais、Mohamed Arbane、Barthelemy Topilko、Jean Brousseau、Clothilde Brochot、Yacine Yaddaden、Ali Bahloul、Xavier Maldague

展开 >

Department of Mathematics, Computer Science, and Engineering, University of Quebec at Rimouski, Rimouski, QC, Canada

Department of Mathematics, Computer Science, and Engineering, University of Quebec at Rimouski, Rimouski, QC, Canada|Institut de Recherche Robert-Sauvé en Santé et en Sécurité du Travail (IRSST), Montreal, QC, Canada

Department of Electrical and Computer Engineering, Laval University, Quebec City, QC, Canada

2025

10.1109/ACCESS.2024.3522562

IEEE Access

IEEE Access

ISSN：
年,卷(期)：2025.13(1)
  • 35